nm-testing
/

fp8_block-e2e

compressed-tensors

Model card Files Files and versions

fp8_block-e2e / recipe.yaml

nm-autobot's picture

Upload folder using huggingface_hub

b3cdaf0 verified 29 days ago

history blame contribute delete

196 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head, 're:.mlp.gate[.].']
	scheme: FP8_BLOCK
	bypass_divisibility_checks: false